Stochastic bottom–up fixation prediction and saccade generation

In this article, a novel technique for fixation prediction and saccade generation will be introduced. The proposed model simulates saccadic eye movement to incorporate the underlying eye movement mechanism into saliency estimation. To this end, a simple salience measure is introduced. Afterwards, we derive a system model for saccade generation and apply it in a stochastic filtering framework. The proposed model will dynamically make a saccade toward the next predicted fixation and produces saliency maps. Evaluation of the proposed model is carried out in terms of saccade generation performance and saliency estimation. Saccade generation evaluation reveals that the proposed model outperforms inhibition of return. Also, experiments signify integration of eye movement mechanism into saliency estimation boosts the results. Finally, comparison with several saliency models shows the proposed model performs aptly.     

Coordinating actions in congestion games: impact of top–down and bottom–up utilities

Congestion games offer a perfect environment in which to study the impact of local decisions on global utilities in multiagent systems. What is particularly interesting in such problems is that no individual action is intrinsically “good” or “bad” but that combinations of actions lead to desirable or undesirable outcomes. As a consequence, agents need to learn how to coordinate their actions with those of other agents, rather than learn a particular set of “good” actions. A congestion game can be studied from two different perspectives: (i) from the top down, where a global utility (e.g., a system-centric view of congestion) specifies the task to be achieved; or (ii) from the bottom up, where each agent has its own intrinsic utility it wants to maximize. In many cases, these two approaches are at odds with one another, where agents aiming to maximize their intrinsic utilities lead to poor values of a system level utility. In this paper we extend results on difference utilities, a form of shaped utility that enables multiagent learning in congested, noisy conditions, to study the global behavior that arises from the agents’ choices in two types of congestion games. Our key result is that agents that aim to maximize a modified version of their own intrinsic utilities not only perform well in terms of the global utility, but also, on average perform better with respect to their own original utilities. In addition, we show that difference utilities are robust to agents “defecting” and using their own intrinsic utilities, and that performance degrades gracefully with the number of defectors.     

Piezoresistive polypropylene–carbon nanofiber composites as mechanical transducers

This paper describes a strain sensor based on a polypropylene–carbon nanofiber (PP–CNF) composite film, fabricated by twin screw extrusion and compression molding, which is an inexpensive industrial polymer production technique. Its working principle is based on the piezoresistive effect showed by this kind of composites. Strain sensing by variation of the electrical resistance of the sensor was tested by a four-point bending method. Furthermore, the dependence of the gauge factor as a function of the deformation and velocity of deformation was calculated. The reproducibility of the electrical response of the material was also tested by applying up to forty loading–unloading cycles. The experimental results showed that PP–CNF films have an overall appropriate response for being used as piezoresistive deformation sensors, with a small non-linear response, typical of composites within the percolation threshold. Finally, electrical equivalent model of the sensor was developed and the experimental data was tested against it, showing good agreement.     

A concurrent red–black tree

With the proliferation of multiprocessor computers, data structures capable of supporting several processes are a growing need. Concurrent data structures seek to provide similar performance to sequential data structures while being accessible concurrently by several processes and providing synchronization mechanisms transparently to those processes.     

Advances in computer–human interaction for detecting facial expression using dual tree multi band wavelet transform and Gaussian mixture model

Neural Computing and Applications - In human communication, facial expressions play an important role, which carries enough information about human emotions. Last two decades, it becomes a very...     

eGHWT: The Extended Generalized Haar–Walsh Transform

Journal of Mathematical Imaging and Vision - Extending computational harmonic analysis tools from the classical setting of regular lattices to the more general setting of graphs and networks is...     

A bottom‐up algorithm for weight‐ and height‐bounded minimal partition of trees

Let T = (V,E) be a rooted tree with n edges. We associate a non‐negative weight w(v) with each vertex v in V. A q‐partition of T into q connected components T₁,...,T_q is obtained by deleting k = q‐1 edges of T, 1<=q<=n. Let w(T_i) denote the sum of the weights of the vertices in T_i. The height of 7] is denoted by h(T_i).

The following problem is considered: Given W, H>0, find a q‐partition satisfying w(T_i) <=W, height (T_i) <=,H (1<=i<=q) for which q is a minimum.

A bottom‐up polynomial time algorithm is given for this problem which has complexity 0(Hn), or independently of H, 0(height(T)n).     

An Extended Perona–Malik Model Based on Probabilistic Models

The Perona–Malik model has been very successful at restoring images from noisy input. In this paper, we reinterpret the Perona–Malik model in the language of Gaussian scale mixtures and derive some extensions of the model. Specifically, we show that the expectation–maximization (EM) algorithm applied to Gaussian scale mixtures leads to the lagged-diffusivity algorithm for computing stationary points of the Perona–Malik diffusion equations. Moreover, we show how mean field approximations to these Gaussian scale mixtures lead to a modification of the lagged-diffusivity algorithm that better captures the uncertainties in the restoration. Since this modification can be hard to compute in practice, we propose relaxations to the mean field objective to make the algorithm computationally feasible. Our numerical experiments show that this modified lagged-diffusivity algorithm often performs better at restoring textured areas and fuzzy edges than the unmodified algorithm. As a second application of the Gaussian scale mixture framework, we show how an efficient sampling procedure can be obtained for the probabilistic model, making the computation of the conditional mean and other expectations algorithmically feasible. Again, the resulting algorithm has a strong resemblance to the lagged-diffusivity algorithm. Finally, we show that a probabilistic version of the Mumford–Shah segmentation model can be obtained in the same framework with a discrete edge prior.     

Human–machine collaboration through vehicle head up display interface

This work introduces a novel design for an automotive full-windshield head-up display (HUD) interface which aims to improve the driver’s spatial awareness and response times under low visibility conditions. To fulfil these requirements, we have designed and implemented a working prototype of a human–machine interface (HMI). Particular emphasis was placed on the prioritisation and effective presentation of information available through vehicular sensors, which would assist, without distracting, the driver in successfully navigating the vehicle under low visibility conditions. The proposed interface is based on minimalist visual representations of real objects to offer a new form of interactive guidance for motorway environments. Overall, this work discusses the design challenges of such a human–machine system, elaborates on the interface design philosophy and presents the outcome of user trials that contrasted the effectiveness of our proposed HUD against a typical head-down display (HDD).     

A verified realization of a Dempster–Shafer based fault tree analysis

Fault tree analysis is a method to determine the likelihood of a system attaining an undesirable state based on the information about its lower level parts. However, conventional approaches cannot process imprecise or incomplete data. There are a number of ways to solve this problem. In this paper, we will consider the one that is based on the Dempster–Shafer theory. The major advantage of the techniques proposed here is the use of verified methods (in particular, interval analysis) to handle Dempster–Shafer structures in an efficient and consistent way. First, we concentrate on DSI (Dempster–Shafer with intervals), a recently developed tool. It is written in MATLAB and serves as a basis for a new add-on for Dempster–Shafer based fault tree analysis. This new add-on will be described in detail in the second part of our paper. Here, we propagate experts’ statements with uncertainties through fault trees, using mixing based on arithmetic averaging. Furthermore, we introduce an implementation of the interval scale based algorithm for estimating system reliability, extended by new input distributions.     

Extended event–condition–action rules and fuzzy Petri nets based exception handling for workflow management

Exception handling plays a key role in dynamic workflow management that enables streamlined business processes. Handling application-specific exceptions is a knowledge-intensive process involving different decision-making strategies and a variety of knowledge, especially much fuzzy knowledge. Current efforts in workflow exception management are not adequate to support the knowledge-based exception handling. This paper proposes a hybrid exception handling approach based on two extended knowledge models, i.e., generalized fuzzy event–condition–action (GFECA) rule and typed fuzzy Petri net extended by process knowledge (TFPN-PK). The approach realizes integrated representation and reasoning of fuzzy and non-fuzzy knowledge as well as specific application domain knowledge and workflow process knowledge. In addition, it supports two handling strategies, i.e., direct decision and analysis-based decision, during exception management. The approach fills in the gaps in existing related researches, i.e., only providing the capability of direct exception handling and neglecting fuzzy knowledge. Based on TFPN-PK, a weighted fuzzy reasoning algorithm is designed to address the reasoning problem of uncertain goal propositions and known goal concepts by combining forward reasoning with backward reasoning and therefore to facilitate cause analysis and handling of workflow exceptions. A prototype system is developed to implement the proposed approach.     

Modal and Intuitionistic Variants of Extended Belnap–Dunn Logic with Classical Negation

In this study, we introduce Gentzen-type sequent calculi BDm and BDi for a modal extension and an intuitionistic modification, respectively, of De and Omori’s extended Belnap–Dunn logic BD+ with classical negation. We prove theorems for syntactically and semantically embedding BDm and BDi into Gentzen-type sequent calculi S4 and LJ for normal modal logic and intuitionistic logic, respectively. The cut-elimination, decidability, and completeness theorems for BDm and BDi are obtained using these embedding theorems. Moreover, we prove the Glivenko theorem for embedding BD+ into BDi and the McKinsey–Tarski theorem for embedding BDi into BDm.

     

An AHP based heuristic DPSO algorithm for generating multi criteria production–distribution plan

Multi-criteria integrated production–distribution problems were solved by many researchers using different optimization techniques. A novel analytic hierarchy process (AHP) based heuristic discrete particle swarm optimization (DPSO) algorithm is proposed in this research for solving difficult production–distribution problems. A bearing manufacturing industry's case is considered in this paper and the mathematical model is formulated as mixed integer linear programming (MILP) problem considering multi-period, multi-product and multi-plant scenarios. The three major objectives considered are total cost reduction, minimization of change in labor levels and percentage under-utilization. The results of the AHP based heuristic DPSO algorithm are compared with the branch and bound algorithm results generated using LINGO software. The approach gives good near optimal solutions. In addition to the bearing manufacturing industry dataset, two other test datasets are also solved.     

Extended Watson–Crick L systems with regular trigger languages and restricted derivation modes

Watson?CCrick Lindenmayer systems add a control mechanism to ordinary Lindenmayer (L) system derivations. The mechanism is inspired by the complementarity relation in DNA strings, and it is formally defined in terms of a trigger language (trigger, for short). It is known that Watson?CCrick E0L systems employed with the standard trigger (which is a context-free language) are computationally universal. Here we show that all recursively enumerable languages can be generated already by a Uni-Transitional Watson?CCrick E0L system with a regular trigger. A system is Uni-Transitional if any derivation of a terminal word can apply the Watson?CCrick morphism at most once. We introduce a weak derivation mode where, for sentential forms in the trigger language, the derivation chooses nondeterministically whether or not to apply the Watson?CCrick morphism. We show that Watson?CCrick E0L systems employing a regular trigger and the weak derivation mode remain computationally universal but, on the other hand, the corresponding Uni-Transitional systems generate only a subclass of the ET0L languages. We consider also the computational power of Watson?CCrick (deterministic) ET0L systems.     

Underwater bottom still mine classification using robust time–frequency feature and relevance vector machine

A novel approach to the problem of detecting and classifying underwater bottom mine objects in littoral environments from acoustic backscattered signals is considered. We begin by defining robust short-time Fourier transform to convert the received echo into a time–frequency (TF) plane. Identify interest local region in spectrogram, then features in TF plane with robustness to reverberation and noise disturbances are built. Finally, echo features are sent to a relevance vector machine (RVM) classifier that represents a Bayesian extension of support vector machine (SVM). To evaluate the performace of the classifier based on this approach, the classification experiment of two typical types of mines lying on the bottom have been performed with a broad bandwidth active sonar. Each of the targets was lying on the lake bottom at a depth of 20 m. The case study exploits the robustness of a feature extraction scheme, and furthermore, RVM yields a much sparser solution and improves the classification accuracy than SVM in an impulse noise environment.     

Extended approach by using best–worst method on the basis of importance–necessity concept and its application

Applied Intelligence - In recent years, several concepts such as fuzzy sets, Z-numbers, and D-numbers have been proposed to handle real-world decision-making problems. Despite the desirable...     

Applicability of the Mix–Unmix Classifier in percentage tree and soil cover mapping

The Mix–Unmix Classifier is a simple novel method developed to address the problem of under‐determination in linear spectral unmixing. This paper tests the applicability of the Mix–Unmix Classifier in percentage mapping of tree cover and different soil types from single bands of satellite imagery. Various transformations were executed on African Moderate Resolution Imaging Spectroradiometer (MODIS) data bands 1, 2, 3, 4, 6 and 7. The equatorial rainforest is most distinguishable under skewness. The skewness transformation band is unmixed into two endmembers: tree (endmember of interest) and non‐tree (background). The resulting percentage tree cover map was compared with a University of Maryland percentage tree cover map of the continent, giving a correlation coefficient of 0.87. Fraction images of three soil types were generated from Japanese Earth Resources Satellite (JERS) synthetic aperture radar (SAR) L‐band data covering a section of Jordan. The soil types considered were hardpan topsoil, Qaa topsoil, and topsoil of herbaceous layer. The correlation coefficients of the Mix–Unmix Classifier‐derived fraction images versus reference fraction images for the three soil types were 0.89, 0.87 and 0.89, respectively.     

Solving a fuzzy multi objective model of a production–distribution system using meta-heuristic based approaches

This paper studies a multi-objective production–distribution system. The objectives are to minimize total costs and maximize the reliability of transportations system. Each transportation system is assumed to be of unique reliability. In the real world, some parameters may be of vagueness; therefore, some tools such as fuzzy logic is applied to tackle with. The problem is formulated using a mixed integer programming model. Commercial software can optimally solve small sized instances. We propose two novel HEURISTICS called ranking genetic algorithm (RGA) and concessive variable neighborhood search (CVNS) in order to solve the large sized instances. RGA utilizes various crossover operators and compares their performances so that better crossover operators are used during the solution process. CVNS applies several neighborhood search structures with a novel learning procedure. The heuristics can recognize which neighborhood structure performs well and applies those more than the others. The results indicated that RGA is of higher performance.     

EMERS: a tree matching–based performance evaluation of mathematical expression recognition systems

Performance evaluation of mathematical expression recognition systems is attempted. The proposed method assumes expressions (input as well as recognition output) are coded following MathML or T_EX/LaT_EX (which also gets converted into MathML) format. Since any MathML representation follows a tree structure, evaluation of performance has been modeled as a tree-matching problem. The tree corresponding to the expression generated by the recognizer is compared with the groundtruthed one by comparing the corresponding Euler strings. The changes required to convert the tree corresponding to the expression generated by the recognizer into the groundtruthed one are noted. The number of changes required to make such a conversion is basically the distance between the trees. This distance gives the performance measure for the system under testing. The proposed algorithm also pinpoints the positions of the changes in the output MathML file. Testing of the proposed evaluation method considers a set of example groundtruthed expressions and their corresponding recognized results produced by an expression recognition system.